Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "assemble_portfolio", "assess_ai_initiative", "calculate_pace_layer_drag" and 10 more
⟨238 unchanged words⟩ is edited, no state exists between calls.Pure deterministicDeterministic calculation,with nonetwork,authentication.auth,Anonymousorusagesidetelemetryeffects.may be sent; set AIBVF_TELEMETRY_DISABLE=1 to opt out.
⟨299 unchanged words⟩ ":"number"}},"type":"object"},"signal_completeness":{"description":"Optional input-quality factor retained for portfolio scoring. Lower it when supplied pillars rest on weak evidence.","maximum":1,"minimum":0,"type":"number"},"work_architecture":{"description":"Evidence that workflows, roles, decision rights and measures are ready. Pass only what is known. Explicit gaps and omitted checks block Accelerate until all four checks are evidenced.","properties":{"decision_rights_defined":{"description":"True only when decision, override and escalation rights have named human owners, false when authority remains unclear.","type":"boolean"},"measures_updated":{"description":"True only when performance measures and incentives reflect the redesigned work, false when the old measures remain.","type":"boolean"},"roles_redesigned":{"description":"True only when affected roles, accountabilities and capability expectations have been rewritten, false when roles remain unchanged.","type":"boolean"},"workflow_redesigned":{"description":"True only when the end-to-end workflow has been redesigned around the AI and retained human judgement, false when the existing workflow remains.","type":"boolean"}},"type":"object"}},"required":["name","function"," ⟨131 unchanged words⟩
⟨138 unchanged words⟩ diagnose_process for measured waste in a running process.Pure deterministicDeterministic calculation,with nonetwork,authentication.authAnonymousorusagesidetelemetryeffects.may be sent; set AIBVF_TELEMETRY_DISABLE=1 to opt out.
⟨264 unchanged words⟩ reports which via pillar_basis and scores_used, decisionconfidencescore is haircut by how much was estimated, ⟨298 unchanged words⟩
⟨142 unchanged words⟩ drag rate, pace-gap severity, drivers and source.Pure deterministicDeterministic calculation—with nonetwork,authentication.auth,Anonymousorusagesidetelemetryeffects.may be sent; set AIBVF_TELEMETRY_DISABLE=1 to opt out.
⟨102 unchanged words⟩ are estimated, because it directly reduces decisionconfidence.score. Use score_initiative for a proposed AI investment and ⟨12 unchanged words⟩ benchmark-cited and figures are directional, not audited.Pure deterministicDeterministic calculation—with nonetwork,authentication.auth,Anonymousorusagesidetelemetryeffects.may be sent; set AIBVF_TELEMETRY_DISABLE=1 to opt out.
⟨115 unchanged words⟩ several initiatives and diagnose_process for measured operational waste.Pure deterministicDeterministic lookup,with nonetwork,authentication.authAnonymousorusagesidetelemetryeffects.may be sent; set AIBVF_TELEMETRY_DISABLE=1 to opt out.
⟨119 unchanged words⟩ question is what to change in that process.Pure deterministicDeterministic calculation,with nonetwork,authentication.auth,Anonymousorusagesidetelemetryeffects.may be sent; set AIBVF_TELEMETRY_DISABLE=1 to opt out.
⟨71 unchanged words⟩ of values to choose from. Takes no parameters.Pure deterministicDeterministic lookup—with nonetwork,authentication.auth,Anonymousorusagesidetelemetryeffects.may be sent; set AIBVF_TELEMETRY_DISABLE=1 to opt out.
⟨91 unchanged words⟩ score_initiative, diagnose_process, get_benchmark or the portfolio tools.Pure deterministicDeterministic lookup,with nonetwork,authentication.auth,Anonymousorusagesidetelemetryeffects.may be sent; set AIBVF_TELEMETRY_DISABLE=1 to opt out.
⟨128 unchanged words⟩ decide whether this remains Fix or becomes Stop.Pure deterministicDeterministic calculation,with nonetwork,authentication.authAnonymousorusagesidetelemetryeffects.may be sent; set AIBVF_TELEMETRY_DISABLE=1 to opt out.
⟨615 unchanged words⟩ reports which via pillar_basis and scores_used, decisionconfidencescore is haircut by how much was estimated, ⟨298 unchanged words⟩
⟨53 unchanged words⟩ deterministically, reported through pillar_basis, and reduce decisionconfidencescore, while a fully estimated pass can never return Accelerate. Returns Accelerate, Fix or Stop, modelled gross andnetreadiness-adjusted EUR benefit ranges, decisionconfidencescore, sensitivity, assumptions and an audit trail. Use ⟨5 unchanged words⟩ diagnose_process for measured waste in an existing process.Pure deterministicDeterministic calculation,with nonetwork,authentication.authAnonymousorusagesidetelemetryeffects.may be sent; set AIBVF_TELEMETRY_DISABLE=1 to opt out.
⟨22 unchanged words⟩ aggregate modelled EUR value range, mean decisionconfidencescore, the highest-value initiative, the highest-risk initiative, ⟨96 unchanged words⟩ the verdicts need turning into a 90-day order.Pure deterministicDeterministic calculation—with nonetwork,authentication.auth,Anonymousorusagesidetelemetryeffects.may be sent; set AIBVF_TELEMETRY_DISABLE=1 to opt out.
{"properties":{"portfolio":{"description":"A portfolio document conforming to the
⟨151 unchanged words⟩ treating its wave placement as permission to proceed.Pure deterministicDeterministic calculation,with nonetwork,authentication.auth,Anonymousorusagesidetelemetryeffects.may be sent; set AIBVF_TELEMETRY_DISABLE=1 to opt out.
⟨112 unchanged words⟩ valid=true or one error per failing JSON path.Pure deterministicDeterministic validation—with nonetwork,authentication.auth,Anonymousorusagesidetelemetryeffects.may be sent; set AIBVF_TELEMETRY_DISABLE=1 to opt out.
Changed the definition of "assess_ai_initiative"
⟨33 unchanged words⟩ AI tier and organisational readiness, then returnstheonenextclarificationmissingcoveringquestionevery unresolved input or an Accelerate, Fix or Stop verdict. Ask that clarification once and call this tool again with the answers in the explicit fields. Use work_architecture to test whether the end-to-end workflow ⟨78 unchanged words⟩
⟨97 unchanged words⟩ Certificate recorded, valid to 2026-12-04
Authorization not required
First tool surface recorded: 13 tools (server version 0.14.11)
Showing the latest 5 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
⟨159 unchanged words⟩ :"string"},"applied_modules":{"description":"BVFScoring-rulescoringandmodulessector-contextthatlabels.firedSectorforlabelsthisdoinput.not certify clinical validation or regulatory compliance.","items":{"type":"string"}, ⟨144 unchanged words⟩ :"string"},"decision_confidence":{"description":"ConfidenceHeuristicindecisionthescore,verdict0 to 100,0-100.adjusted for input quality. This score has no probability calibration.","type":"number"},"drivers":{ ⟨74 unchanged words⟩ ,"high"],"type":"object"},"interpretation":{"additionalProperties":{"type":"string"},"description":"Meaning and limits of compatibility fields. Present these labels when explaining the result.","type":"object"},"multipliers":{"description":"Factors applied to the ⟨21 unchanged words⟩ :"object"},"net_value_eur":{"description":"ModelledReadiness-adjustednetbenefitvaluehypothesisinbeforeEURprojectafterbuild,capturerunrate,andlow/high.change costs. Replace planning rates with scoped economics before funding.","properties":{"high":{"type": ⟨174 unchanged words⟩ when readiness is already siloed.","type":["object","null"]},"revenue_minus_20pct":{"type":"object"}, ⟨99 unchanged words⟩
⟨656 unchanged words⟩ ,"url"],"type":"object"},"interpretation":{"additionalProperties":{"type":"string"},"description":"Meaning and limits of compatibility fields. Present these labels when explaining the result.","type":"object"},"notes":{"description":"Caveats or context on ⟨7 unchanged words⟩ :"array"},"projected_decision_confidence":{"description":"ConfidenceProjectedinheuristicthedecisionverdictscore,if0thetorecommendations100.land,The0-100.target remains conditional on work architecture and evidence review.","type":"number"},"recommendations":{ ⟨102 unchanged words⟩
⟨350 unchanged words⟩ reports which via pillar_basis and scores_used, decisionconfidencescore is haircut by how much was estimated, ⟨298 unchanged words⟩ object"},"signal_completeness":{"description":"Optional0–1. How grounded the four pillar scores are in real evidence versus estimated from context. Defaults0 to 1(treated as measured). If the organisation lacks formal change-readiness or riskinput-qualitymetadata,factor.estimateThethedefaultpillarsranges fromwhat you0.5knowwhenANDallsetpillarsthisarelowerestimated tosay so1—whendecisionallconfidenceareissupplied.reducedSuppliedproportionallyvaluesandstillarequirecaveatevidenceisreview.attached,Lowerinsteadthisoffactorreturningwhenathefalselysuppliedconfidentpillarsverdictrest onsoftweakinputs.evidence.","maximum":1,"minimum":0,"type":"number"},"work_architecture":{"description":"Optional evidenceEvidence thattheworkflows,workroles,arounddecisiontherightsAIandhasmeasuresbeenareredesigned.ready. Pass only what is known.AnyExplicitexplicitgapsfalseandvalueomittedblockschecks block Accelerate untilthe gap is closed;allomittedfour checksremain visible asareunknown.evidenced.","properties":{"decision_rights_defined":{"description": ⟨97 unchanged words⟩
⟨11 unchanged words⟩ :"string"},"applied_modules":{"description":"BVFScoring-rulescoringandmodulessector-contextthatlabels.firedSectorforlabelsthisdoinput.not certify clinical validation or regulatory compliance.","items":{"type":"string"}, ⟨144 unchanged words⟩ :"string"},"decision_confidence":{"description":"ConfidenceHeuristicindecisionthescore,verdict0 to 100,0-100.adjusted for input quality. This score has no probability calibration.","type":"number"},"drivers":{ ⟨74 unchanged words⟩ ,"high"],"type":"object"},"interpretation":{"additionalProperties":{"type":"string"},"description":"Meaning and limits of compatibility fields. Present these labels when explaining the result.","type":"object"},"multipliers":{"description":"Factors applied to the ⟨21 unchanged words⟩ :"object"},"net_value_eur":{"description":"ModelledReadiness-adjustednetbenefitvaluehypothesisinbeforeEURprojectafterbuild,capturerunrate,andlow/high.change costs. Replace planning rates with scoped economics before funding.","properties":{"high":{"type": ⟨174 unchanged words⟩ when readiness is already siloed.","type":["object","null"]},"revenue_minus_20pct":{"type":"object"}, ⟨90 unchanged words⟩
⟨15 unchanged words⟩ :"string"},"aggregate_net_value_eur":{"description":"SumArithmeticofsumnetofEURbenefitvaluehypotheses.acrossReconcilescoredoverlappinginitiativesscope,low/high.double counting and project costs before using this as a portfolio business case.","properties":{"high":{"type": ⟨109 unchanged words⟩ ,"reason"],"type":"object"},"interpretation":{"additionalProperties":{"type":"string"},"description":"Meaning and limits of compatibility fields. Present these labels when explaining the result.","type":"object"},"mean_decision_confidence":{"description":"Mean decisionconfidencescore across scored initiatives (0–100); 0 when ⟨51 unchanged words⟩ :"string"},"applied_modules":{"description":"BVFScoring-rulescoringandmodulessector-context labels. Sector labels do not certify clinical validation or regulatory compliance.","items":{"type":"string"},"type":"array"},"audit":{"description":"Reproducibility record: engine version, the rules that fired,forandthistheinitiative.resolved inputs. Deterministic, no timestamps. If the verdict is challenged months later, the same inputs on the same engine version reproduce it exactly.","properties":{"bvf_version":{"type":"string"},"engine":{"type":"string"},"engine_version":{"type":"string"},"inputs_used":{"description":"The resolved inputs the result was computed on, including estimated pillar values.","type":"object"},"note":{"type":"string"},"rules_fired":{"description":"The rules that actually fired, in order: estimation, gates, classification, value arithmetic.","items":{"type":"string"},"type":"array"}},"type":"object"},"caveat":{"description":"Present only when signal_completeness was low: warns the verdict rests on soft inputs and confidence was reduced.","type":"string"},"classification":{"enum":["Accelerate","Fix" ⟨2 unchanged words⟩ :"string"},"decision_confidence":{"description":"ConfidenceHeuristicindecisionthescore,verdict0(0–100).to 100, adjusted for input quality. This score has no probability calibration.","type":"number"},"function":{ ⟨7 unchanged words⟩ string"},"net_value_eur":{"description":"Modellednetreadiness-adjusted EURvaluebenefit, low/high.","properties":{"high":{" ⟨7 unchanged words⟩ ,"high"],"type":"object"},"pillar_basis":{"description":"Per pillar: \"given\" (caller supplied it) or \"estimated\" (deterministic prior). When any pillar is estimated, tell the user which, and ask for evidence on those to firm up the verdict.","properties":{"change_enablement":{"enum":["given","estimated"],"type":"string"},"financial_return":{"enum":["given","estimated"],"type":"string"},"governance_risk":{"enum":["given","estimated"],"type":"string"},"strategic_alignment":{"enum":["given","estimated"],"type":"string"}},"type":"object"},"reason":{"type":"string"},"scores_used":{"description":"The four pillar values the verdict was actually computed on, whether given by the caller or estimated by the engine. Show these to the user when any pillar was estimated.","properties":{"change_enablement":{"type":"number"},"financial_return":{"type":"number"},"governance_risk":{"type":"number"},"strategic_alignment":{"type":"number"}},"type":"object"},"sensitivity":{"description":"What moves this verdict, computed deterministically: the value if readiness were one notch worse, the value at revenue minus 20 percent, and the nearest single-pillar movements that flip the classification. Boards trust ranges with visible assumptions over point estimates; show this.","properties":{"readiness_one_notch_down":{"description":"Null when readiness is already siloed.","type":["object","null"]},"revenue_minus_20pct":{"type":"object"},"verdict_flips":{"items":{"type":"string"},"type":"array"}},"type":"object"},"signal_completeness":{"description":"Input-quality factor after estimated provenance, pillar quality and any explicit factor are combined conservatively.","maximum":1,"minimum":0,"type":"number"},"work_architecture":{"description":"The work architecture gate across workflow, roles, human decision rights and performance measures. A stated gap or missing evidence blocks Accelerate.","properties":{"blocks_accelerate":{"type":"boolean"},"checks":{"items":{"type":"object"},"type":"array"},"gaps":{"items":{"type":"string"},"type":"array"},"gate":{"type":"string"},"next_question":{"type":"string"},"status":{"enum":["unknown","partial","gap","ready"],"type":"string"},"unknowns":{"items":{"type":"string"},"type":"array"}},"required":["status","blocks_accelerate","checks","gaps","unknowns","gate"],"type":"object"}},"required":["id","name","function","ai_tier"," ⟨105 unchanged words⟩ description":"Scored initiative with the highest mid-pointnetreadiness-adjusted EURvalue.benefit. Omitted when none were scored.","properties": ⟨12 unchanged words⟩ :"string"},"net_value_eur":{"description":"NetReadiness-adjusted EURvaluebenefit range for the top initiative.","properties": ⟨87 unchanged words⟩
⟨15 unchanged words⟩ :"array"},"next_question":{"description":"TheOnesingleclarificationnextcoveringquestioneverytounresolvedask.input. Present only when status isneeds_input.needs_input; ask it once, then call the tool again with the answers in the explicit fields.","type":"string"},"proposal":{ ⟨682 unchanged words⟩